2601.09085v1.pdf

{
  "dorsal/arxiv": [
    {
      "date_modified": "2026-02-17T05:53:20.223000Z",
      "hash": "89c8b5e5cac23effe27714e4e1cd85c34512750699679f2c6ae513962ef94acd",
      "id": "19c1ed9f-32ac-4199-ac56-da7d68d67539",
      "source": {
        "execution_id": "9945831d-3eab-4d67-9e9e-eb9b2f411e4f",
        "id": "arXiv Dataset",
        "type": "Model",
        "variant": "snapshot-2026-01-17",
        "version": "0.1.0"
      },
      "user_id": 1000002
    }
  ],
  "file/base": {
    "record": {
      "extension": ".pdf",
      "hash": "89c8b5e5cac23effe27714e4e1cd85c34512750699679f2c6ae513962ef94acd",
      "media_type": "application/pdf",
      "media_type_prefix": "application",
      "name": "2601.09085v1.pdf",
      "size": 1289339
    },
    "source": {
      "execution_id": "1ee87736-8f2c-47b4-91db-9e3f682ad031",
      "id": "file/base",
      "type": "Model",
      "version": "1.0.0"
    }
  },
  "file/pdf": {
    "private": false,
    "record": {
      "keywords": [],
      "page_count": 21,
      "producer": "pikepdf 8.15.1",
      "title": "MMR-GRPO: Accelerating GRPO-Style Training through Diversity-Aware Reward Reweighting",
      "version": "1.7"
    },
    "source": {
      "execution_id": "a9daddc7-92da-4731-8be8-88f0336e1ea9",
      "id": "dorsal/pdf",
      "type": "Model",
      "version": "1.1.0"
    }
  }
}